
(using ADetailer for all images). Using weight 0.8 in main prompt & 1 in adetailer.
LoRA for Jinora from The Legend of Korra.
V Illustrious; using at weight 1, can check preview for outfit triggers
V2.5 Final:
Outfit trigger: yellow collar, red bodysuit, grey sleeves, fingerless gloves, red pants, knee boots
might have to put "double_bun" in negative as it likes to do double instead of single, even then it's not perfect. tattoos are still hit or miss.
V2:
Recommended weight between 0.6-0.8; can go higher or lower depending on additional LoRAs, etc.
Outfits: wingsuit, airbender robes (easier to prompt on heigher weights)
Tattoo: blue-arrow forehead tattoo, blue-arrow body tattoos
Used Hi-Res Fix (Latent) 2x from 512x512 —> Extras (4x-UltraSharp) for final 2048x2048 resolution.
描述:
works better w/ 2.5D. 19th epoch. new dataset and training method.
训练词语: j1n0ra, blue-arrow forehead tattoo, arrow \(symbol\), brown eyes, short hair, single_bun,,yellow collar, red bodysuit, grey sleeves, fingerless gloves, red pants, knee boots
名称: j1n0ra.safetensors
大小 (KB): 18549
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success